WO2006096478A2 - Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique - Google Patents

Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique Download PDF

Info

Publication number
WO2006096478A2
WO2006096478A2 PCT/US2006/007502 US2006007502W WO2006096478A2 WO 2006096478 A2 WO2006096478 A2 WO 2006096478A2 US 2006007502 W US2006007502 W US 2006007502W WO 2006096478 A2 WO2006096478 A2 WO 2006096478A2
Authority
WO
WIPO (PCT)
Prior art keywords
layers
cells
layer
recognition
cell
Prior art date
Application number
PCT/US2006/007502
Other languages
English (en)
Other versions
WO2006096478A3 (fr
Inventor
Klaus J. Bach
Original Assignee
Bach Klaus J
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bach Klaus J filed Critical Bach Klaus J
Priority to EP06736767.2A priority Critical patent/EP1866841A4/fr
Publication of WO2006096478A2 publication Critical patent/WO2006096478A2/fr
Publication of WO2006096478A3 publication Critical patent/WO2006096478A3/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]

Definitions

  • the invention relates to a method and system for implementing successive multi-layered feature recognition in N-dimensional space in which recognition cells are dynamically generated to accommodate the input data and are adapted during the recogni- tion process, wherein the recognition cells are structured into groups which have specific recognition features assigned to them.
  • Pattern and object recognition by means of successive computa- tion steps generally begins with the loading of an input data- set into a pre-defined set of input variables or cells which constitute the lowest recognition layer.
  • each cell in higher recognition layers generates a response based on the values or responses of a selected sub- set of cells in lower layers (receptive field) .
  • the number of layers used, the sizes of the receptive fields, and the rule used by each cell to compute its response vary depending on the type of information to be recognized, that is, the complexity and number of the patterns, and the intermediate features that must be recognized to successfully identify the pattern.
  • Sufficiently fine-grained intermediate features, overlapping receptive fields, and strongly converging data paths enable distortion-invariant and position-tolerant recognition.
  • the structure and dimension of the recognition layers are generally fixed during the recognition process, requiring that each layer contain enough recognition cells to fill the N dimensions of the recognition space in the required resolution. For cases where N > 2 the resulting large number of cells makes a computation of the cell responses unfeasible. The process becomes inefficient particularly where the input data is sparsely distributed throughout a large input space.
  • the structure of a neural recognition network is dynamically gener- ated and adapted to recognize an object.
  • the layers of the network are capable of recognizing key features of the input data by using evaluation rules to establish a hierarchical structure that can adapt to data position and orientation, varying data densities, geometrical scaling, and faulty or missing data. Based on successive hierarchical feature recognition and synthesis, sufficient relevant recognition cells are generated to enable data processing and information propagation through the recognition network without generating or computing unnecessary irrelevant cells.
  • a network hierarchy is defined and constructed comprising a succession of recognition layers which each contain a collection of nodes or cells.
  • the number of cells in a layer varies during processing, and each layer is initially equipped with zero cells.
  • Each layer recognizes a specific group of key features, and the cells in the layer are used to represent the presence and characteristics of the fea- tures .
  • the layers are interlinked by ownership-type relationships in which a cell in a given layer is said to own a group of cells in a subordinate layer, and this subordinate group of cells is said to constitute the receptive field of the su- perordinate cell.
  • This owner-subordinate relationship is re- peated between each pair of successive layers from the lowest input layer to the final uppermost recognition layer.
  • This final layer represents the answer to the overall recognition problem in that its cells recognize the key features that uniquely classify the pattern imposed on the input layer.
  • Each layer represents an abstraction level of the object to be recognized, with the complexity of the abstraction being greater in the higher layers.
  • Each layer is equipped with a set of key features that characterize an aspect or property of the object to be recognized, with said features being computable by examining the properties and responses of a subset of cells in the subordinate layer.
  • Each layer is equipped with a rule or algorithm for determining whether a subordinate layer cell contributes positively or negatively to the recognition process carried out in said layer, specifi- cally, a means of determining whether the inclusion of a given subordinate cell in the receptive field of a given superordinate cell is advantageous to the recognition function of the superordinate cell.
  • All cells have the further following properties: l.A 1-dimensional response vector (fuzzy polarization vector) which indicates the cell' s recognition of the features which are key to the layer containing the cell.
  • cells in the various hierarchi- cal layers may be created and destroyed, linked and unlinked with owners, and assigned to, and removed from, receptive fields in an iterative convergent process that can implement neural network recognition techniques that result in a final collection of cells that adequately represents the object to be recognized in the various hierarchical layers.
  • This final structure is both a hierarchical map of the input data as well as a network capable of recognizing the key features of the input data.
  • superordinate cells extract features by evaluating the properties of the subordinate cells in their receptive fields, and subordinate cells base their membership decisions, receptive field sizes, and evaluation parameters on information from the superordinate layer cells. Recognition occurs when the top-down signals and bottom-up signals are sufficiently mutually fortifying to establish a persistent stable activation level of all involved cells; at this point the iterative proc- ess has converged to a solution.
  • the computation process is initiated by transferring the input data into the lowest hierarchical layer (the input or zeroth layer) .
  • Typical input data may consist of simply a list of co- ordinates and a physical property that has been measured at that coordinate.
  • a single input cell may be generated for each input data point, fully representing the input data with zero information loss.
  • the next superordinate layer is constructed by means of an appropriate rule or algorithm for grouping input layer cells.
  • the input layer cells are divided into a number of groups, a new layer 1 cell is generated for each group, the receptive field pointers of the layer 1 cell are set to point to the cells in the group, and the cells in the group become owned by the new layer 1 cell.
  • This initial grouping into receptive fields is repeated as each new layer is constructed, and, although the iterative solution process converges despite ill- defined initial groupings, a well-planned initial grouping speeds convergence.
  • the iterative solution process may begin, and may continue throughout and af- ter the successive construction of the third to last layers.
  • the iterative process may implement whatever neural network recognition techniques are appropriate to the key features of the relevant layer, generally simple analytical formulae in the lower layers, and more complex pattern recognition algorithms in the higher layers, but always driving toward a stable state of mutual inter-layer reinforcement.
  • receptive field sizes and recognition parameters are adjusted, cells may reselect the receptive field to which they belong based on new information from higher layers, and cells may even find there is no existing receptive field they wish to join.
  • Superordinate cells are created as required to overtake ownership of orphaned cells, and are destroyed when their receptive fields have atrophied.
  • the flexible dynamic structure has the following ⁇ advantages :
  • D Cells are generated only where there is data to recognize D Receptive field sizes are dynamic and membership criteria are based on rules, allowing receptive fields to adapt to varying data densities and geometric scaling of key features (the network is scale invariant)
  • a typical problem well suited for this network algorithm is 3- dimensional object recognition using as input data a set of 3- dimensional coordinate points representing random points on the surface of the object to be recognized.
  • Such a dataset could be generated, for example by a laser scanning device capable of detecting and outputting the 3-dimensional coordinates of its scan points.
  • Scan data generated in an industrial plant setting for the purposes of documentation, computation, and analy- sis has a usefulness that is directly related to the degree or complexity of recognition, or intelligence. For example, recognizing the mere presence of a surface is accomplished by a laser scan, but is not very useful; to recognize that surface as a part of a cylinder is better, but to recognize it as part of a pipe of a certain size with specific end connections allows the generation of useful CAE models of existing plants.
  • the input data consists of a 3- dimensional laser scan of a section of an industrial plant.
  • the current implementation uses 5 layers abstracted as follows (that is, what a cell from each layer represents) :
  • D Layer 2 Curved or flat surface fragment
  • D Layer 3 Geometric primitive (cylinder, box, edge, sphere)
  • D Layer 4 Final 3-d object
  • the input layer of the network is filled with input data such that one input layer cell is generated for each scanned laser point and assigned the spatial coordinates of the scan point.
  • a cell in this layer can only represent a spatial point, there- fore its polarization vector has only one component which always has a value of 1.
  • the next step constructs Layer 1 by finding an unowned layer 0 cell, generating a new layer 1 cell as its owner, and searching in the neighborhood of the previously unowned layer 0 cell for other unowned layer 0 cells that can be added to the receptive field of the new layer 1 cell. This process is repeated until there are no unowned layer 0 cells.
  • a layer 1 cell in this implementation can only represent a small surface patch locally approximated as flat, and therefore also has a polarization ⁇ -vector that has only one component which always has a value of 1.
  • each layer 1 cell now has a group of layer 0 cells which it owns and which form its receptive field. From these cells, the layer 1 cell can evaluate itself and recognize the features it is assigned to recognize. Since the cells of layer 1 are intended to represent flat surface patches or panels, they can be appropriately represented by the coordinates of their centroid and by a 3-dimensional vector representing the surface normal at the centroid, whereby these values can be computed by simple analytical formulae applied to the layer 0 cells in the receptive field. Once the layer 1 cells have been evaluated, the rule can be applied which judges the contribution of a layer 0 cell to the recognition process of the layer 1 cell to which it belongs.
  • a layer 0 cell Since a layer 1 cell represents a flat surface panel, a layer 0 cell contributes poorly or detrimentally to the recognition process of the layer 1 cell if it does not lie in or near the plane represented by the layer 1 cell. In this case, the layer 0 cell is removed from the receptive field of the layer 1 cell and allowed to search for an other more appropriate layer 1 cell to join. If that search is unsuccessful, the orphaned layer 0 cell initiates a new layer 1 cell to own it. During successive iterations, that newly generated receptive field, which at first contains a single layer 0 cell, may grow by the acquisition of other layer 0 cells that are rejected from nearby receptive fields.
  • each layer 0 cell is owned by a layer 1 cell, and each layer 1 cell has a well-defined receptive field with members that support the decision of the recognition process carried out by the layer 1 cell.
  • all input data has been processed without loss of information, in that each input data point has generated a layer 0 cell, and each layer 0 cell has been given the opportunity to represent the surface to which it belongs in the layer 1 surface panels.
  • the layer 2 cells are constructed by a similar process: for each unowned layer 1 cell, a new layer 2 cell is created and allowed to search for further receptive field members.
  • the layer 2 cells can represent various types of surface elements, including curved surfaces, they have additional properties or variables to represent the features unique to this recognition layer (strength of curvature, that is, radius of curvature, and curvature orientation) and a two-component polarization vector to indicate the type of surface represented (flat or curved) .
  • These properties can be computed from the cells of the receptive field, and the layer 2 cells can be optimized by an iterative process as was done for the layer 1 cells.
  • the conditions for membership in the receptive field of a layer 2 cell differ, however, from the conditions for membership in the receptive field of a layer 1 cell. Since layer 2 cells may represent curved surfaces, they must be more lenient in their selection of members, also allowing layer 1 cells to join that have their centroids somewhat outside the average plane represented by the layer 2 cell. On the other hand, layer 2 cells may impose new membership conditions on layer 1 cells, for example requiring that the receptive field of a layer 1 cell lie adjacent to the receptive field of another layer 1 cell that is already a member of the layer 2 cell's receptive field before allowing membership.
  • Top-down information flow may contribute to the recognition process in the following way: once a radius of curvature has been computed for a layer 2 cell, it becomes clear that that cell represents a curved surface segment that is "likely to be part of a cylinder or sphere. For the purpose of recognizing that cylinder or sphere, it is not necessary and makes no sense to include information from points that are a distance of more that twice the computed radius of curvature away from the computed center. Thus it is possible for a layer 2 cell to restrict the size of the receptive fields of the layer 1 cells it owns to a certain value, and to allow the layer 1 cells to reevaluate themselves based on this new information.
  • Layer 3 cells are then generated and optimized analogous to layer 1 and 2 cells.
  • Layer 3 cells are built up from the features of layer 2 cells, and represent cylindrical segments, edges, boxes, and whatever other geometric primitives are nec- essary to represent the objects found in the input data.
  • Layer 3 cells again contain properties or variables not found in layer 2 cells to assess the key features detected, and a four- component polarization vector to specify the type of object the layer 3 cell represents.
  • the polarization vector of a cell indicates the degree to which the cell belongs to one of the recognition categories and serves to assess the compatibility between cells of differing layers.
  • the polarization vector tends toward one of the following states: [l 0 0 ⁇ ] s Plane
  • the po- larization vector is set to [1 1 1 1] meaning that the cell is simultaneously a flat plane, an edge, a cylinder, and a sphere.
  • the polarization vector is refined and asymptotically approaches one of the states listed above.
  • the polarization vector is used in conjunction with a compatibility matrix to assess the utility or feasibility of including a given layer 2 cell in the receptive field of a given layer 3 cell. This is carried out by multiplying the polarization vec- tor of the layer 3 cell with the compatibility matrix and with the polarization vector of the layer 2 cell:
  • layer 4 cells represent the answer to the recognition problem in that they are abstractions of elements which are a more intelligent and more complete representation of the data than the original layer 0 data points.

Landscapes

  • Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)
  • Character Discrimination (AREA)

Abstract

Cette invention concerne un procédé et un système servant à la mise en oeuvre de la reconnaissance d'objets en réseau multicouche dans un espace N-dimensionnel, dans lesquels la structure d'un réseau de reconnaissance neuronal est générée dynamiquement et adaptée pour reconnaître un objet. Les couches du réseau sont capables de reconnaître les caractéristiques clés des données d'entrée en utilisant des règles d'évaluation pour établir une structure hiérarchique qui peut s'adapter à la position et à l'orientation des données, à la variation des densités de données, à l'évolution de l'échelle géométrique et aux données défectueuses ou manquantes.
PCT/US2006/007502 2005-03-04 2006-03-02 Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique WO2006096478A2 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP06736767.2A EP1866841A4 (fr) 2005-03-04 2006-03-02 Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US11/072,880 2005-03-04
US11/072,880 US20060204097A1 (en) 2005-03-04 2005-03-04 Method and system for implementing N-dimensional object recognition using dynamic adaptive recognition layers

Publications (2)

Publication Number Publication Date
WO2006096478A2 true WO2006096478A2 (fr) 2006-09-14
WO2006096478A3 WO2006096478A3 (fr) 2007-05-24

Family

ID=36953864

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2006/007502 WO2006096478A2 (fr) 2005-03-04 2006-03-02 Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique

Country Status (3)

Country Link
US (2) US20060204097A1 (fr)
EP (1) EP1866841A4 (fr)
WO (1) WO2006096478A2 (fr)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8874498B2 (en) 2011-09-16 2014-10-28 International Business Machines Corporation Unsupervised, supervised, and reinforced learning via spiking computation
US8738554B2 (en) 2011-09-16 2014-05-27 International Business Machines Corporation Event-driven universal neural network circuit
US8626684B2 (en) 2011-12-14 2014-01-07 International Business Machines Corporation Multi-modal neural network for universal, online learning
US8799199B2 (en) 2011-12-14 2014-08-05 International Business Machines Corporation Universal, online learning in multi-modal perception-action semilattices
KR101388749B1 (ko) * 2013-10-25 2014-04-29 중앙대학교 산학협력단 3차원 데이터로부터 3차원 산업 모델을 구축하는 시스템 및 방법
KR101364375B1 (ko) 2013-10-25 2014-02-18 중앙대학교 산학협력단 3차원 데이터로부터 특정 객체를 추출하는 시스템 및 방법.
US11664125B2 (en) * 2016-05-12 2023-05-30 Siemens Healthcare Gmbh System and method for deep learning based cardiac electrophysiology model personalization
US10895954B2 (en) * 2017-06-02 2021-01-19 Apple Inc. Providing a graphical canvas for handwritten input
WO2019003046A1 (fr) * 2017-06-27 2019-01-03 株式会社半導体エネルギー研究所 Terminal d'information portable et système de résolution de problèmes
CN108509949B (zh) * 2018-02-05 2020-05-15 杭州电子科技大学 基于注意力地图的目标检测方法
CN108990833A (zh) * 2018-09-11 2018-12-14 河南科技大学 一种基于位置信息的动物运动行为判别方法及装置
CN112016638B (zh) * 2020-10-26 2021-04-06 广东博智林机器人有限公司 一种钢筋簇的识别方法、装置、设备及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4355301A (en) * 1980-05-27 1982-10-19 Sumitomo Electric Industries, Ltd. Optical character reading system
US4975975A (en) * 1988-05-26 1990-12-04 Gtx Corporation Hierarchical parametric apparatus and method for recognizing drawn characters
US5295198A (en) * 1988-10-14 1994-03-15 Harris Corporation Pattern identification by analysis of digital words

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of EP1866841A4 *

Also Published As

Publication number Publication date
EP1866841A4 (fr) 2013-12-18
EP1866841A2 (fr) 2007-12-19
US20070258649A1 (en) 2007-11-08
US8059890B2 (en) 2011-11-15
WO2006096478A3 (fr) 2007-05-24
US20060204097A1 (en) 2006-09-14

Similar Documents

Publication Publication Date Title
WO2006096478A2 (fr) Procede et systeme pour la mise en oeuvre de la reconnaissance d'objets n-dimensionnels au moyen de couches de reconnaissance adaptative dynamique
CN111299815B (zh) 一种用于低灰度橡胶垫视觉检测与激光切割轨迹规划方法
Chow et al. Surface registration using a dynamic genetic algorithm
Thanathamathee et al. Handling imbalanced data sets with synthetic boundary data generation using bootstrap re-sampling and AdaBoost techniques
Ghaseminezhad et al. A novel self-organizing map (SOM) neural network for discrete groups of data clustering
Kerschke et al. Cell mapping techniques for exploratory landscape analysis
CN105376791B (zh) 基于sub-Voronoi图面积法的动态传感器网络覆盖空洞检测修复方法
CN106373118A (zh) 可有效保留边界和局部特征的复杂曲面零件点云精简方法
Zheng et al. A geometric approach to automated fixture layout design
CN115563674A (zh) 初始平面布置生成方法和装置、电子设备和存储介质
Ding et al. A contemporary study into the application of neural network techniques employed to automate CAD/CAM integration for die manufacture
CN109345571B (zh) 一种基于扩展高斯图像的点云配准方法
CN107515960B (zh) 基于特征建模的循环对称筒形支撑结构拓扑优化设计方法
Krishnanand et al. Glowworm swarm optimization for searching higher dimensional spaces
Solar et al. Proximity load balancing for distributed cluster-based individual-oriented fish school simulations
Ahmad et al. A multi-agent based approach for particle swarm optimization
Khrissi et al. A feature selection approach based on archimedes’ optimization algorithm for optimal data classification
Hamfelt et al. Beyond K-means: clusters identification for GIS
CN116310780A (zh) 基于轮廓建模的光学遥感图像任意方向船只目标检测方法
Wolny et al. Improving population-based algorithms with fitness deterioration
Hamdani et al. Enhancing the structure and parameters of the centers for BBF fuzzy neural network classifier construction based on data structure
Liu et al. Particle swarm optimization based clustering: a comparison of different cluster validity indices
Nelson et al. Topology-preserving dimensionality reduction via interleaving optimization
CN114629798B (zh) 多智能体协同规划方法、装置、电子设备及存储介质
Xiong et al. Machine vision for 3D mechanical part recognition in intelligent manufacturing environments

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2006736767

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: RU